Stars
Schema-first state machines for Effect. Define once, derive everywhere, break nothing.
Type-safe StarRocks SDK for TypeScript. Effect.ts services, Schema DSL, Stream Load, 2PC transactions, query builder, and migrations.
A frontend-independent IDE "smartness" server for Elixir. Implements the "Language Server Protocol" standard and provides debugger support via the "Debug Adapter Protocol"
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
BlAInder range scanner is a Blender add-on to simulate Lidar and Sonar measurements. The result can be saved as annotated 2D image or 3D point cloud.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. The knowledge is av…
Local Twitter/X bookmark organizer with AI categorization and mindmap visualization
⛅ A collection of WASM packages those work on Cloudflare Workers
This repo hosts a one-click-deploy Cloudflare worker that proxies RPC requests to Helius.
The next generation web framework for Cloudflare Workers
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
Trade autonomously on Polymarket using AI Agents
Define, test, and document APIs like a developer, not a SaaS user. No accounts. No lock-in. No telemetry. Just Markdown, Git, hotkeys, and your damn specs.
Property-based testing for web UIs, autonomously exploring and validating correctness properties, finding harder bugs earlier
Simple, yet powerful Web- & Product Analytics.
Open-source and self-hostable wallet key management. Create non-custodial wallets for users in Ethereum and Solana
Scripts for agents, shared between my repositories.
Fastest Robotics Runtime System. If phones have Android, robots deserve HORUS.
A guide for how to use your smartphone to code anywhere at anytime.
A comprehensive guide to running autonomous AI coding loops using Geoff Huntley's Ralph methodology. View as formatted guide below 👇
Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...)
Working memory for Claude Code - persistent context and multi-instance coordination
A coding agent hook that acts as a safety net, catching destructive git and filesystem commands before they execute.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
High-performance AI routing proxy built in Rust with automatic failover, priority-based routing, and support for 15+ providers (Anthropic, OpenAI, Cerebras, Minimax, Kimi, etc.)